A hairiness detection method based on the fusion of maximum entropy and dbscan

A detection method and maximum entropy technology, which can be used in image analysis, image enhancement, instruments, etc., to solve problems such as inability to accurately calculate hairiness length and incomplete hairiness extraction.

Active Publication Date: 2019-11-19
XI'AN POLYTECHNIC UNIVERSITY
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a hairiness detection method based on the fusion of maximum entropy and DBSCAN, which solves the problem that the hairiness extraction is incomplete and the length of hairiness cannot be accurately calculated in the existing detection algorithm

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • A hairiness detection method based on the fusion of maximum entropy and dbscan
  • A hairiness detection method based on the fusion of maximum entropy and dbscan
  • A hairiness detection method based on the fusion of maximum entropy and dbscan

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0076] A hairiness detection method based on the fusion of maximum entropy and DBSCAN, specifically implemented according to the following steps:

[0077] Step 1, scale the yarn image to be detected to 256×256 pixels, and convert it to single-channel BMP format;

[0078] Step 2, performing bilateral filtering on the yarn image obtained after step 1;

[0079] Specifically: take each pixel in the yarn image as the target pixel in turn, mark the coordinates of each target pixel as (i, j), and mark the coordinates of the pixels in the neighborhood of each target pixel as (k, l), according to the pixel value f(k,l) of the pixel point in the neighborhood of each target pixel point, the pixel value g(i,j) of each target pixel point after filtering is obtained, as shown in formula (1):

[0080]

[0081] In formula (1), ω(i, j, k, l) is the weighting coefficient, and its calculation formula is shown in formula (2):

[0082]

[0083] In formula (2), σ d and σ r Both are smooth...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a hairiness detection algorithm based on the fusion of maximum entropy and DBSCAN, specifically: firstly, the image of the yarn to be detected is scaled to 256×256 pixels, and converted into a single-channel BMP format, and the yarn The yarn image is subjected to bilateral filtering processing, and then the maximum entropy threshold is used to segment the yarn image, and then the yarn image processed by the optimal threshold is processed by the open operation to refine the yarn hairiness, and finally the density clustering algorithm is used to refine the yarn image. The hairiness of the final yarn image is processed to obtain the number and length of hairiness. This method uses the maximum entropy threshold to process the yarn image when extracting the hairiness, which can preserve the complete information of the hairiness to the greatest extent, and avoid the situation that the hairiness is segmented and disconnected during the thresholding process. At the same time, combined with the DBSCAN clustering algorithm, the number of hairs and the length of each hair is counted, with high accuracy and small error.

Description

technical field [0001] The invention belongs to the technical field of textile detection, and in particular relates to a hairiness detection method based on the fusion of maximum entropy and DBSCAN. Background technique [0002] Hairiness can affect the appearance and feel of the yarn and the final textile. For example, the distribution of hairiness on two weft yarns is different, which will cause a difference in the degree of reflection, thereby forming a rung on the cloth surface; uneven hairiness will lead to uneven dyeing, excessive hairiness The place where there is less color is darker, and the color where there is less is lighter, resulting in color difference; the yarn with more hairiness is easy to be rubbed and pilled during processing, thereby reducing the quality of the textile. To form high-quality textiles, it is fundamental to produce high-quality yarns. Therefore, the detection and evaluation of yarn appearance quality plays a decisive role in improving the q...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G06T7/00G06T7/11G06T7/136G06T7/155G06K9/62
CPCG06T7/0004G06T7/11G06T7/136G06T7/155G06T2207/20028G06T2207/30124G06F18/23
Inventor 张缓缓严凯李仁忠景军锋李鹏飞
Owner XI'AN POLYTECHNIC UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap